広告掲載
MCP.so
ログイン

ArcGIS MCP Bridge

@muend

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

muend

投稿者

Muhammed Enes Duran

ArcGIS MCP Bridge について

Secure local-first MCP server exposing 100 ArcGIS Pro / ArcPy geoprocessing tools to LLM agents. Two-process architecture, PathGuard filesystem sandboxing, and confirmation gates for destructive operations. Real geoprocessing requires local Windows + licensed ArcGIS Pro; cloud/co

#arcgis#gis#geospatial#arcpy#esri#geoprocessing#spatial-analysis#geoai

ArcGIS MCP Bridge の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "arcgis-mcp-bridge": {
      "command": "arcgis-mcp-server",
      "env": {
        "ARCPY_PYTHON_PATH": "C:\\path\\to\\arcgis-mcp-env\\python.exe",
        "ARCGIS_MCP_ALLOWED_ROOTS": "C:\\GIS\\Data",
        "ARCGIS_MCP_MAX_WORKERS": "2"
      }
    }
  }
}

ArcGIS MCP Bridge のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is ArcGIS MCP Bridge?

A secure, local-first, asynchronous MCP server exposing ArcGIS Pro’s ArcPy engine to Claude Desktop and other MCP hosts over stdio JSON-RPC. It provides 100 declarative geoprocessing tools across 10 verticals with a two-process isolation architecture that keeps the MCP protocol layer separate from the licensed ArcPy runtime.

How to use ArcGIS MCP Bridge?

Install the package via pip install arcgis-mcp-bridge or uv pip install arcgis-mcp-bridge. Set the required ARCPY_PYTHON_PATH environment variable to the licensed worker interpreter, optionally configure ARCGIS_MCP_ALLOWED_ROOTS and other settings, then add the server to your Claude Desktop configuration with the command arcgis-mcp-server. After restart, call health_check first to verify the full pipeline.

Key features of ArcGIS MCP Bridge

  • 100 declarative geoprocessing tools across 10 verticals
  • Two-process architecture isolating arcpy from the MCP server
  • PathGuard sandbox enforcing read/write boundaries on filesystem access
  • Destructive mutation safety floor requiring explicit confirm tokens
  • Sketch-to-GIS pipeline for hand-drawn polygon digitization
  • 81 unit tests with mocked arcpy for CI verification

Use cases of ArcGIS MCP Bridge

  • Buffer parcels, dissolve layers, or run kernel density from natural language prompts
  • List, describe, and manage feature classes in enterprise or file geodatabases
  • Calculate slope, aspect, and hillshade from DEM rasters
  • Find nearest facilities or compute OD cost matrices using network analysis
  • Convert hand-drawn sketch to a GIS feature class via the vision analytics pipeline

よくある質問

1

How does ArcGIS MCP Bridge compare to other ArcGIS MCP servers?

It offers 100 tools versus ~15 or ~10 in alternatives, uses deterministic `uv.lock` dependency sync, stdio

コメント

「開発者ツール」の他のコンテンツ

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

1

CircleCI MCP Server

CircleCI

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents

Nebelus

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

Ramen

bkraad47

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

3
広告掲載